Skip to content

MAVLab

Micro Air Vehicle Lab – TUDelft

home
  • News
  • Research
    • Research Summary
    • Research
      • Robots
      • Code
      • Datasets
      • Competitions
    • Projects
      • Events
    • Spinoffs
  • People
  • Education
    • University Courses
    • Other
  • Publications and Datasets
    • Publications
    • Datasets
  • Media
  • Awards
  • Jobs
  • Contact
  • News
  • Research
    • Research Summary
    • Research
      • Robots
      • Code
      • Datasets
      • Competitions
    • Projects
      • Events
    • Spinoffs
  • People
  • Education
    • University Courses
    • Other
  • Publications and Datasets
    • Publications
    • Datasets
  • Media
  • Awards
  • Jobs
  • Contact

Category: Research

Research

Taming Contrast Maximization for Learning Sequential, Low-latency, Event-based Optical Flow

Posted onAugust 11, 2023September 25, 2024

    Federico Paredes-Vallés, Kirk W. Y. Scheper, Christophe De Wagter, Guido C. H. E. de Croon   Event cameras have recently gained significant traction …

News, Research

AvoidBench @ ICRA 2023

Posted onJune 1, 2023October 18, 2023

At ICRA (IEEE International Conference on Robotics and Automation) 2023, MAVLab presented AvoidBench, a high-fidelity vision-based obstacle avoidance benchmarking suite for multi-rotors. Motivation Vision-based obstacle …

News, Research

Nature article reveals how flying insects and drones can discern up from down

Posted onOctober 19, 2022October 19, 2022

Researchers from MAVLab and collaborators have developed a new theory on how flying drones and insects can estimate the gravity direction. Whereas drones typically use …

News, Research

Insect-inspired AI for autonomous robots

Posted onJune 15, 2022June 15, 2022

Insect-inspired AI for autonomous robots Small autonomous mobile robots, such as drones, rovers, and legged robots, promise to perform a wide range of tasks, from …

Research

Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networks

Posted onOctober 25, 2021September 25, 2024

    Jesse J. Hagenaars*, Federico Paredes-Vallés*, Guido C.H.E. de Croon   The field of neuromorphic computing promises extremely low-power and low-latency sensing and processing. …

Autonomous swarm of tiny drones finds gas leaks
News, Research

Swarm of autonomous tiny drones can localize gas leaks

Posted onJuly 14, 2021December 10, 2021

A gas leak in a large building or at an industrial site is difficult to find. Human firefighters cannot see the gas, so they have …

News, Research

Learning process as a Solution to Fundamental Optical-flow Problems

Posted onJanuary 19, 2021December 10, 2021

Optical flow for small flying robots Flying insects heavily rely on optical flow for visual navigation and flight control. Roboticists have endowed small flying robots …

News, Robots

TU Delft maritime hydrogen drone flies longer and greener

Posted onNovember 10, 2020November 10, 2020

    A drone that can fly sustainably for long distances over land and water, and can land almost anywhere, will be able to serve …

News, Robots

Neuromorphic control for optic-flow-based landings of MAVs using the Loihi processor

Posted onNovember 3, 2020November 4, 2020

    Neuromorphic processors like Loihi offer a promising alternative to conventional computing modules for endowing constrained systems like micro air vehicles (MAVs) with robust, …

Research

Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy

Posted onSeptember 16, 2020September 25, 2024

F. Paredes-Valles, G. C. H. E. de Croon Event cameras are novel vision sensors that sample, in an asynchronous fashion, brightness increments with low latency …

Posts pagination

‹ 1 2 3 4 5 ‹
© 2025 MAVLab Powered by WordPress Theme by Design Lab